New AI-Enabled Virtual Screening Tool Identifies Most Promising Approved Drugs for Success in Treating COVID‑19

Model Can Reduce Drug Discovery Timeline for Other Diseases

NEW YORK, Feb. 18, 2021 /PRNewswire/ — WorldQuant Predictive (WQP), an AI predictive products company, and CAS, a division of the American Chemical Society that specializes in scientific information solutions, have partnered to develop a groundbreaking methodology that can save time and lives by helping research teams rapidly prioritize the most promising drug candidates to treat COVID-19 and other critical diseases. The scientific paper detailing this methodology and collaboration was recently published in the peer-reviewed journal, ACS Omega.

Overlaying WQP’s novel AI technology platform, Quanto™, with the exhaustive repository of data from the CAS REGISTRY®, the groundbreaking initiative was led by WQP scientific advisor and former Pfizer Senior Vice President in research and development, Kelvin Cooper, Ph.D. The goal of this project was to create a virtual screening tool model that can be replicated by outside researchers and biopharmaceutical companies to quickly identify compounds to treat COVID-19 and other diseases. Using a well-studied medicinal chemistry tool known as quantitative structure activity relationships, or QSAR, the team evolved the model from human-led input.

“The promise of AI and machine learning has always been to make better, faster predictions,” said Jim Golden, CEO of WorldQuant Predictive. “This new AI-enabled virtual screening tool is a quicker, more assured path to helping medical researchers identify cures across disease states, including other emerging viruses.  It can cut critical time off the search for cures, virtually screening for successful therapies in a week instead of the typical six to eight months.”

This project applied AI tools such as feature engineering, embedding, and other novel modeling techniques in crucial areas. The result is smarter detection of patterns that might otherwise not be seen by researchers, enabling them to distinguish compounds based on a target fingerprint.

“The COVID-19 pandemic has served as a powerful accelerator of collaboration and technology opportunities within healthcare,” said CAS President Manuel Guzman. “This project demonstrates the power of uniting the complementary expertise and assets of two highly specialized organizations to accelerate solutions for an urgent problem. The resulting approach has great potential beyond COVID-19 to expedite drug discovery pipelines for other critical diseases.”

The findings, along with a detailed description of the methodology, key data sets, and identified candidates are available to the research community on the WorldQuant Predictive website.

###

About WorldQuant Predictive

WorldQuant Predictive is the market leader in quantitative predictions, leveraging artificial intelligence and machine learning to rapidly create a predictive edge for organizations. WorldQuant Predictive was founded by Igor Tulchinsky. The firm’s cloud-based platform enables data-driven decisions at scale. Its combination of global quantitative talent and proprietary technology gives clients the power to quickly see around corners, and make better, more proactive decisions. WorldQuant Predictive is a separate entity from WorldQuant, LLC, a global quantitative asset management firm. For more information, visit https://wqpdev.wpengine.com/

About CAS

CAS, a division of the American Chemical Society specializing in scientific information solutions, partners with R&D organizations globally to provide actionable insights that help them plan, innovate, protect their innovations, and predict how new markets and opportunities will evolve. Scientists, patent professionals and business leaders rely on CAS solutions and services to advise discovery and strategy. With more than 110 years’ experience, no one knows more about scientific information than CAS. For more information, visit www.cas.org

Contact

Wayne Henninger
wayne@waynehenninger.com
570.573.6556

Posted in